Yaochu Jin received the B.Sc., M.Sc., and Ph.D. degrees, all in automatic control from Zhejiang University, Hangzhou, China, in 1988, 1991, and 1996, respectively, and the Dr.-Ing. Degree in Computer Science from Ruhr University Bochum, Germany, in 2001.
Dr Jin is currently Full Professor and Chair in Computational Intelligence, Department of Computing, University of Surrey, UK, where he also heads the Nature Inspired Computing and Engineering (NICE) Group. Priori to joining Surrey, he was Principal Scientist and Group Leader at the Honda Research Institute Europe. His main research interests include computational approaches to understanding evolution, learning and development in biology, and bio-inspired approaches to complex systems design. He has (co)edited four books and three conference proceedings, authored a monograph, and (co)authored over 150 peer-reviewed journal and conference papers. His papers have reported over 4400 citations, of which more than 1400 were included in ISI Web of Science.
Dr Jin is an Associate Editor of BioSystems, the IEEE Transactions on Neural Networks, the IEEE Transactions on Nanobioscience, the IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, and the IEEE Computational Intelligence Magazine. He is also an Area Editor of Soft Computing. He is Chair of the 2007, 2009, 2011 IEEE Symposium on Computational Intelligence in Multi-Criterion Decision-Making, General Chair of 2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, General Chair of 2013 UK Workshop on Computational Intelligence and Program Chair of 2013 IEEE Congress on Evolutionary Computation. He is a Fellow of BCS and Senior Member of IEEE.
Modeling Activity-Dependent Plasticity in BCM Spiking Neural Networks with Application to Human Behavior Recognition
Spiking neural networks are considered to be computationally more powerful than conventional neural networks. However, the capability of spiking neural networks in solving complex real-world problems remains to be demonstrated. In this paper, we propose a substantial extension of the Bienenstock, Cooper, and Munro (BCM) spiking neural network model, in which the plasticity parameters are regulated by a gene regulatory network (GRN). Meanwhile, the dynamics of the GRN is dependent on the activation levels of the BCM neurons. We term the whole model GRN-BCM. To demonstrate its computational power, we first compare the GRN-BCM with a standard BCM, a hidden Markov model and a reservoir computing model on a complex time series classification problem. Simulation results indicate that the GRN-BCM significantly outperforms the compared models. The GRN-BCM is then applied to two widely used datasets for human behavior recognition. Comparative results on the two datasets suggest that the GRN-BCM is very promising for human behavior recognition, although the current experiments are still limited to the scenarios in which only one object is moving in the considered video sequences.